© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 11879
    Prev
    Next
    INDEX
    Explanations

    verb forms of 'to be'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" in various contexts, often related to descriptions and status updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fail
    -0.77
    dB
    -0.72
    Cause
    -0.70
    ulence
    -0.69
     interven
    -0.68
    aceae
    -0.67
     externalToEVAOnly
    -0.66
    querade
    -0.65
    yout
    -0.63
     Fail
    -0.62
    POSITIVE LOGITS
     averaging
    1.29
     slated
    1.13
     expected
    1.07
     projected
    1.04
     owed
    1.04
     poised
    1.02
     nearing
    1.01
     eligible
    1.01
     reportedly
    0.95
     entering
    0.95
    Activations Density 0.111%

    No Known Activations